Land‐use dynamic discovery based on heterogeneous mobility sources

Nowadays, cities are the most relevant type of human settlement and their population has been endlessly growing for decades. At the same time, we are witnessing an explosion of digital data that capture many different aspects and details of city life. This allows detecting human mobility patterns in urban areas with more detail than ever before. In this context, based on the fusion of mobility data from different and heterogeneous sources, such as public transport, transport‐network connectivity and Online Social Networks, this study puts forward a novel approach to uncover the actual land use of a city. Unlike previous solutions, our work avoids a time‐invariant approach and it considers the temporal factor based on the assumption that urban areas are not used by citizens all the time in the same manner. We have tested our solution in two different cities showing high accuracy rates.     

降维方法监督分类的比较研究

对ISOMap、LDA、LLE、PCA这4种典型降维算法的主要思想和算法步骤进行了详细分析,并将它们用于有监督分类。从实验结果分析得到结论 ,其可为有监督分类提供有益的借鉴。     

The clustering-based case-based reasoning for imbalanced business failure prediction: a hybrid approach through integrating unsupervised process with supervised process

Case-based reasoning (CBR) is one of the main forecasting methods in business forecasting, which performs well in prediction and holds the ability of giving explanations for the results. In business failure prediction (BFP), the number of failed enterprises is relatively small, compared with the number of non-failed ones. However, the loss is huge when an enterprise fails. Therefore, it is necessary to develop methods (trained on imbalanced samples) which forecast well for this small proportion of failed enterprises and performs accurately on total accuracy meanwhile. Commonly used methods constructed on the assumption of balanced samples do not perform well in predicting minority samples on imbalanced samples consisting of the minority/failed enterprises and the majority/non-failed ones. This article develops a new method called clustering-based CBR (CBCBR), which integrates clustering analysis, an unsupervised process, with CBR, a supervised process, to enhance the efficiency of retrieving information from both minority and majority in CBR. In CBCBR, various case classes are firstly generated through hierarchical clustering inside stored experienced cases, and class centres are calculated out by integrating cases information in the same clustered class. When predicting the label of a target case, its nearest clustered case class is firstly retrieved by ranking similarities between the target case and each clustered case class centre. Then, nearest neighbours of the target case in the determined clustered case class are retrieved. Finally, labels of the nearest experienced cases are used in prediction. In the empirical experiment with two imbalanced samples from China, the performance of CBCBR was compared with the classical CBR, a support vector machine, a logistic regression and a multi-variant discriminate analysis. The results show that compared with the other four methods, CBCBR performed significantly better in terms of sensitivity for identifying the minority samples and generated high total accuracy meanwhile. The proposed approach makes CBR useful in imbalanced forecasting.     

基于语言模型的有监督词义消歧模型优化研究

词义消歧是自然语言领域中重要的研究课题之一。目前,有监督词义消歧方法已经是解决该问题的有效手段。但是,由于缺乏大规模的训练语料,有监督方法还不能取得满意的效果。该文提出一种基于语言模型的词义消歧优化模型,该模型采用语言模型优化传统的有监督消歧模型,充分利用有监督和语言模型两种模型的消歧优势,共同推导歧义词的词义。该模型可以在训练语料不足的情况下,有效的提高词义消歧效果。在真实数据上表明,该方法的消歧性能超过了参加SemEval-2007:task #5评测任务的最好的有监督词义消歧系统。     

基于流形学习的整体正交稀疏保留鉴别分析

稀疏保留投影是一种有效的特征提取方法,但是其主要关注样本间的全局稀疏重构关系,并且得到的投影变换通常不是正交的。在实际应用中,图像数据往往处于高维空间中的一种低维流形中,正交性一直被认为有利于提高鉴别能力。文中以有监督学习的方式在稀疏保留投影中引入了流形结构保留,并使得投影空间正交,从而提出了一种新的特征提取方法,即基于流形学习的整体正交稀疏保留鉴别分析（MLHOSDA）。在人脸和掌纹图像数据库的实验结果表明此方法具有较好的识别效果。     

应用于临床生存时间预测的二次学习算法研究

生存时间预测在医学、经济和工程等领域有着广泛的应用。随着机器学习技术和数据挖掘技术的发展和广泛应用,研究人员提出了很多基于机器学习技术的生存时间预测算法。这些算法虽然都取得了良好的效果,但预测精度均有提升的空间。因此,提出了一种基于二次学习风范的生存时间预测算法,并结合最近邻算法在截尾样本估计上的应用以及支持向量机在泛化性能上的优势,实现了对临床生存时间的建模。实验结果表明,该算法能够获取精确的生存时间,且具有预测精度上的性能优势。     

基于多通道分离整合的多尺度单幅图像去雨算法

由于密度不同的雨对图像造成的遮挡不同,图像去雨一直都是一项极具挑战性的任务。目前,基于深度学习的图像去雨算法已经成为主流。然而,多数深度学习的架构都是通过堆叠卷积层来设计的,执行去雨任务后图像仍存在着大小不一的雨痕,这些方法并不能很好地关注训练中雨图的局部信息和上下文信息。为了解决上述问题,本文设计一种基于多通道分离整合的卷积神经网络用于图像去雨。第一步通过通道分离,再利用卷积层间的层级连接,构成多尺度模块,最终将不同通道的输出进行整合。该模块可以增大感受野,探索特征图之间的空间信息,更好地提取特征。第二步利用渐进网络来反复计算挖掘上下文信息,能够很好关联到全局特征。整体模型易于实施,可以端对端训练。在常用的数据集以及自建的自动驾驶雨天数据集上的大量实验表明,本文方法比现有方法取得了明显的改进。     

基于自动编码器的深度伪造图像检测方法

基于深度学习的图像伪造方法生成的图像肉眼难辨,一旦该技术被滥用于制作虚假图像和视频,可能会对国家政治、经济、文化造成严重的负面影响,也可能会对社会生活和个人隐私构成威胁。针对上述问题,提出了一种基于自动编码器的深度伪造Deepfake图像检测方法。首先,借助高斯滤波对图像进行预处理,提取高频信息作为模型输入;然后,利用自动编码器对图像进行特征提取,并在编码器中添加注意力机制模块以获取更好的分类效果;最后,通过消融实验证明,采用所提的预处理方法和添加注意力机制模块有助于伪造图像检测。实验结果表明,与ResNet50、Xception以及InceptionV3相比,所提方法在数据集样本量较小且包含的场景丰富时,可以有效检测多种生成方法所伪造的图像,其平均准确率可达97.10%,明显优于对比方法,且其泛化性能也明显优于对比方法。     

在线半监督Kohonen网络的预抓取手势识别

为实现智能仿生手的抓取,提高模式识别的实时性和灵敏性,提出一种在线半监督Kohonen网络。该网络针对表面肌电信号(s EMG)的特性,在有监督Kohonen网络基础上,将有监督和无监督网络的优势进行结合,应用数据剪辑方法处理训练集更新识别网络,在线识别侧边抓取、球形抓取、三指精确抓取和圆柱形抓取4种预抓取手势。实验表明,与不同Kohonen网络相比,此识别方法具有很好的在线识别能力和正确率。     

Efficient Learning of Relational Object Class Models

We present an efficient method for learning part-based object class models from unsegmented images represented as sets of salient features. A model includes parts’ appearance, as well as location and scale relations between parts. The object class is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model’s parameters, however, are optimized to reduce a loss function of the training error, as in discriminative methods. We show how boosting techniques can be extended to optimize the relational model proposed, with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features. The method has an advantage over purely generative and purely discriminative approaches for learning from sets of salient features, since generative method often use a small number of parts and features, while discriminative methods tend to ignore geometrical relations between parts. Experimental results are described, using some bench-mark data sets and three sets of newly collected data, showing the relative merits of our method in recognition and localization tasks.